Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Code and math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     περί
    -0.07
    ternet
    -0.07
    شمالی
    -0.06
    agas
    -0.06
    oooo
    -0.06
     �
    -0.06
     Seminar
    -0.06
    VISIBLE
    -0.06
     Maurit
    -0.06
    Recommended
    -0.06
    POSITIVE LOGITS
    istency
    0.06
    activate
    0.06
     mùi
    0.06
     Egyptians
    0.06
     threaten
    0.06
    333
    0.06
     naz
    0.06
    successful
    0.06
    альну
    0.06
     Judaism
    0.06
    Act Density 0.001%

    No Known Activations